def findCenters(newickFile, switchLo, switchHi, lossLo, lossHi):
"""This function takes as input a .newick file in the form
<filename>.newick, and low and high values for costscape for both
switches and losses. It returns a list of the centroids of each region in
the costscape associated with the given .newick file."""
hostTree, parasiteTree, phi = newickFormatReader(newickFile)
CVlist = reconcile.reconcile(parasiteTree, hostTree, phi, switchLo,
switchHi, lossLo, lossHi)
coordList = plotcosts.plotcosts(CVlist, lossLo, lossHi, switchLo,
switchHi, "", False, False)
polygonList = getNewCoordList(newickFile, switchLo, switchHi, lossLo,
lossHi)
pointList = []
for i in range(len(polygonList)):
point = polygonList[i]
numCommas = point.count(",")
if numCommas > 1:
# polygon case
region = load_wkt(point)
pointList.append(region.centroid.wkt)
elif numCommas == 1:
# line case
x1 = coordList[i][0][0]
y1 = coordList[i][0][1]
x2 = coordList[i][1][0]
y2 = coordList[i][1][1]
midx = (x1 + x2) * 1.0 / 2
midy = (y1 + y2) * 1.0 / 2
pointList.append("POINT ({} {})".format(str(midx), str(midy)))
else:
# point case
pointList.append("POINT {}".format(str(coordList[i][0])))
return pointList
def newickToTreeParser(newickFile):
try:
outFile = tempfile.NamedTemporaryFile(delete=False)
host, parasite, phi = newickFormatReader(newickFile)
H = treeFormat(host)
P = treeFormat(parasite)
H_dict = {} # name:index
P_dict = {} # name:index
count = 0
for key in H:
count += 1
H_dict[key] = count
for key in P:
count += 1
P_dict[key] = count
outFile.write("HOSTTREE\n")
for key in H:
outFile.write(str(H_dict[key]) + "\t")
if H[key] == [None, None]:
outFile.write("null\tnull\n")
else:
outFile.write(str(H_dict[H[key][0]]) + "\t" + str(H_dict[H[key][1]]) + "\n")
outFile.write("\nHOSTNAMES\n")
for key in H:
outFile.write(str(H_dict[key]) + "\t" + key + "\n")
outFile.write("\nPARASITETREE\n")
for key in P:
outFile.write(str(P_dict[key]) + "\t")
if P[key] == [None, None]:
outFile.write("null\tnull\n")
else:
outFile.write(str(P_dict[P[key][0]]) + "\t" + str(P_dict[P[key][1]]) + "\n")
outFile.write("\nPARASITENAMES\n")
for key in P:
outFile.write(str(P_dict[key]) + "\t" + key + "\n")
outFile.write("\nPHI\n")
for key in phi:
outFile.write(str(H_dict[phi[key]]) + "\t" + str(P_dict[key]) + "\n")
outFile.close()
return outFile.name
except CheetaError:
raise
except:
raise CheetaError(CheetaErrorEnum.FileParse,
newickFile, "Could not parse file - Check to see file formatting is correct")
def reconcile(fileName, D, T, L):
"""Takes as input a newick file, FileName, a dupliction cost, a transfer
cost, and a loss cost. This uses newickFormatReader to extract the host
tree, parasite tree and tip mapping from the file and then calls DP to
return the DTL reconciliation graph of the provided newick file"""
try:
host, paras, phi = newickFormatReader(fileName)
return DP(host, paras, phi, D, T, L)
except CheetaError:
raise
except:
raise CheetaError(CheetaErrorEnum.Alg), None, sys.exc_info()[2]
def getNewCoordList(newickFile, switchLo, switchHi, lossLo, lossHi):
"""Takes as input a newick file in the form <filename>.newick, and low
and high values for costscape for both switches and losses. Returns a
list of strings, where each string contains all the verteces of one
region from costscape."""
hostTree, parasiteTree, phi = newickFormatReader(newickFile)
CVlist = reconcile.reconcile(parasiteTree, hostTree, phi, switchLo,
switchHi, lossLo, lossHi)
coordList = plotcosts.plotcosts(CVlist, lossLo, lossHi, switchLo,
switchHi, "", False, False)
newCoordList = []
for vertexList in coordList:
string = "POLYGON(("
for vertex in vertexList:
string = "{}{} {},".format(string, str(vertex[0]), str(vertex[1]))
string = "{}))".format(string[:-1])
newCoordList.append(string)
return newCoordList
def Reconcile(argList):
"""Takes command-line arguments of a .newick file, duplication, transfer,
and loss costs, the type of scoring desired and possible switch and loss
ranges. Creates Files for the host, parasite, and reconciliations"""
fileName = argList[1] # .newick file
D = float(argList[2]) # Duplication cost
T = float(argList[3]) # Transfer cost
L = float(argList[4]) # Loss cost
freqType = argList[5] # Frequency type
# Optional inputs if freqType == xscape
switchLo = float(argList[6]) # Switch lower boundary
switchHi = float(argList[7]) # Switch upper boundary
lossLo = float(argList[8]) # Loss lower boundary
lossHi = float(argList[9]) # Loss upper boundary
try:
host, paras, phi = newickFormatReader(fileName)
hostRoot = ReconciliationGraph.findRoot(host)
# Default scoring function (if freqtype== Frequency scoring)
DTLReconGraph, numRecon, cost = DP.DP(host, paras, phi, D, T, L)
# uses xScape scoring function
# if freqType == "xscape":
# DTLReconGraph = calcCostscapeScore.newScoreWrapper(fileName, switchLo, \
# switchHi, lossLo, lossHi, D, T, L)
# uses Unit scoring function
if freqType == "unit":
DTLReconGraph = unitScoreDTL(host, paras, phi, D, T, L)
DTLGraph = copy.deepcopy(DTLReconGraph)
scoresList, recs = Greedy.Greedy(DTLGraph, paras)
infeasible_recs = []
for rec in recs:
if orderGraph.date(ReconciliationGraph.buildReconciliation(host, paras, rec)) == False:
infeasible_recs.append(rec)
except CheetaError:
raise
except:
raise CheetaError(CheetaErrorEnum.Alg), None, sys.exc_info()[2]
return infeasible_recs, recs, cost
